From an operational perspective, I appreciate the use of automated GitHub workflows to keep the documentation up-to-date. However, I'd like to see more information on the monitoring and logging mechanisms in place to ensure the system's reliability and performance.

One practical thing you might add is a `max_budget` field on the grant that the user can set when authorizing, so the client can’t accidentally burn through the whole credit pool in a single request. Also, when you stream responses you embed `credits_charged` only in the final SSE chunk – consider also sending a provisional estimate in each data frame so the client can abort early if it’s about to exceed the budget.